Dockerfile

FROM pytorch/pytorch:2.8.0-cuda12.8-cudnn9-runtime
# has python3.11

# Install system dependencies
RUN apt-get update && apt-get install -y \
    ffmpeg \
    libsndfile1 \
    g++ \
    && rm -rf /var/lib/apt/lists/*

WORKDIR /app

# Copy requirements and install
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt
# Install Flash Attention 2 using pre-built wheels (requires torch to be installed first)
RUN pip install packaging
#RUN pip install flash-attn --no-build-isolation --no-cache-dir
RUN pip install https://github.com/Dao-AILab/flash-attention/releases/download/v2.8.3/flash_attn-2.8.3+cu12torch2.8cxx11abiTRUE-cp311-cp311-linux_x86_64.whl

# Copy application code
COPY main.py .

# Expose port 8080
EXPOSE 8080

ENV PYTHONUNBUFFERED=1

# Start uvicorn
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8080", "--log-level", "debug"]